Nowadays, the protection and inheritance of traditional culture are facing unprecedented challenges. Against this background, this study selects traditional ceramic culture with profound cultural deposits as the resea...
详细信息
ISBN:
(纸本)9798400707032
Nowadays, the protection and inheritance of traditional culture are facing unprecedented challenges. Against this background, this study selects traditional ceramic culture with profound cultural deposits as the research object, aiming to explore how to utilize modern scientific and technological means, especially information technology, to promote and strengthen the inheritance of traditional culture. We use collaborative filtering algorithms to build a learning environment based on collaboration and cooperation, which analyzes and processes user behavioral data to recommend learners with similar interests or needs to collaborate with each other, thus improving learning efficiency and depth of cultural understanding. In the knowledge test score, it went from 65-70 at the beginning to nearly 80;and in the skill assessment score, it improved from below 75 to about 90. It is found that this approach not only effectively promotes communication and interaction among learners and increases learning motivation, but also enhances learners' understanding and skill mastery of ceramic culture in a relatively short period of time.
Predictive machinelearning models nowadays are often updated in a stateless and expensive way. The two main future trends for companies that want to build machinelearning based applications and systems are real-time...
详细信息
This document presents the 3nd international Conference on Visual pattern Extraction and recognition for Cultural Heritage Understanding (VIPERC 2024), a premier forum for presenting academic and industry papers on bi...
详细信息
The number of institutions engaged in credit business is increasing, the types of credit products are constantly enriched, and the credit balance is growing rapidly, which has led to an increasing demand for intellige...
详细信息
ISBN:
(纸本)9798400707032
The number of institutions engaged in credit business is increasing, the types of credit products are constantly enriched, and the credit balance is growing rapidly, which has led to an increasing demand for intelligent credit risk management. Pre-loan review is the most core stage in credit risk management, and a good pre-loan risk prediction model can minimize future risks. Some small and medium-sized banks still use traditional mathematical and statistical methods for risk prediction, which can neither meet the growing business needs of credit risk prediction nor guarantee the quality of prediction. Based on the research results of domestic and foreign scholars in the field of customer credit default prediction, this paper proposes a bank credit risk prediction management model based on a multi-level deep neural network to address the limitations of small and medium-sized banks using traditional methods based on mathematical statistics for risk prediction. Using the actual loan data of a commercial bank as experimental data, the simulation experimental results show that the model has a high prediction accuracy.
Given the impact of the learning and lifestyle of contemporary student groups on their physical health quality, as well as the unique characteristics of the elderly population, effective monitoring methods are needed....
详细信息
ISBN:
(纸本)9798400707032
Given the impact of the learning and lifestyle of contemporary student groups on their physical health quality, as well as the unique characteristics of the elderly population, effective monitoring methods are needed. At the same time, health data should be visualized and uploaded to cloud platforms. Through real-time tracking and precise analysis of data, a clearer understanding of health status can be obtained, and scientific life adjustments can be made. This article designs a health monitoring system for real-time data measurement and remote data transmission. The system is mainly divided into two parts: device side and OneNET cloud platform server. The device side uses stM32 as the control core, mainly collecting, displaying, and uploading health data. If the data is abnormal, the device promptly reminds relevant personnel. The device uses a WIFI module to connect to the network and uploads data to OneNET cloud platform through the MQTT protocol. This article focuses on device side design, and also briefly introduce the configuration of the OneNET platform.
This study is focused on improving the dependability and precision of weather forecasting by employing the capabilities of Artificial Intelligence. Specifically, this study utilizes Logistic Regression and machine Lea...
详细信息
ISBN:
(纸本)9798400707032
This study is focused on improving the dependability and precision of weather forecasting by employing the capabilities of Artificial Intelligence. Specifically, this study utilizes Logistic Regression and machinelearning techniques to forecast weather, demonstrating the potential in optimizing weather-related activities and disaster management strategies. The study relies on comprehensive weather data observed over several years, sourced from Kaggle, and handles missing data and outliers during its pre-processing stages. The primary machinelearning tool applied is Logistic Regression, followed by a stepwise feature selection to identify influential features for accurate weather prediction. The workflow also involves data collection, pre-processing, model building, training, and testing, with provisions for handling both numeric and categorical features along with imputations. The accuracy, precision, and recall of the prediction module are tested using appropriate statistical tools. The Logistic Regression model, upon implementation, demonstrated considerable accuracy, with an ability to predict rainy days and non-rainy days efficiently. An analytical approach was used to examine the model's sensitivity towards the removal of each feature, thereby ascertaining the relative importance of each. Critical predictors like 'Rainfall', 'Pressure9am', and 'WindGustSpeed' exhibited significant effects on the probability of rain. Overall, the use of Logistic Regression and machinelearning techniques notably improved rain prediction, offering potential for further advancements in the field of weather forecasting.
Since the status of carbon emission indicators involves many factors, there is often a problem of large errors when evaluating them. For this reason, this paper proposes a study on a carbon emission indicator evaluati...
详细信息
ISBN:
(纸本)9798400707032
Since the status of carbon emission indicators involves many factors, there is often a problem of large errors when evaluating them. For this reason, this paper proposes a study on a carbon emission indicator evaluation method that integrates machinelearning and multi-modal data. After comprehensively analyzing the influencing factors of the value of carbon emission rights from the four perspectives of macroeconomics, energy prices, climate change, policy, and the international carbon market, we integrated multi-modal influencing factor data, calculated the corresponding carbon emission costs, and combined them as the input characteristic parameter of the BP neural network, through forward propagation and backward propagation, the linear relationship between it and the value of carbon emission rights is determined, and the corresponding model is constructed to realize the value evaluation of carbon emission rights. In the test results, the fit between the carbon emission rights value assessment results and the actual transaction price has always remained relatively stable, and the specific error has always been within 0.70 yuan/ton, with the maximum error being only 0.66 yuan/ton. Compared with the control group, it has obvious advantages in assessment accuracy and effectiveness respectively.
Robust principal component analysis (PCA) is an important data dimensionality reduction algorithm. The traditional method to measure recovery error by F-norm is highly sensitive to noise. This paper proposed a modifie...
详细信息
ISBN:
(纸本)9798400707032
Robust principal component analysis (PCA) is an important data dimensionality reduction algorithm. The traditional method to measure recovery error by F-norm is highly sensitive to noise. This paper proposed a modified two-dimension Robust PCA (M2DRPCA). M2DRPCA uses L-p,L-q-norm to measure the recovery error and introduces the joint regularization term of L-1,L-1-norm and F-norm to constrain the low-dimensional representation matrix of the sample, which enhances the robustness to noise and effectively avoids overfitting. An algorithm for solving M2DRPCA is presented. considering that the subproblem can be divided into some blocks, the alternate direction multiplier method (ADMM) is proposed to solve M2DRPCA. The result of numerical experiments shows that M2DRPCA has smaller recovery error than other models, which proves the effectiveness of the work.
The traditional malicious URL identification methods usually adopt blacklist technology, heuristic algorithm and machinelearning algorithm. This paper considers that natural language processing technology can be intr...
详细信息
ISBN:
(纸本)9798400707032
The traditional malicious URL identification methods usually adopt blacklist technology, heuristic algorithm and machinelearning algorithm. This paper considers that natural language processing technology can be introduced when dealing with text with context. This technique is used to help computers understand, interpret, and manipulate human language. It is often used to deal with contextual problems, and when combined with malicious URL directions, it can produce more accurate models than existing methods. In addition to the traditional TF-IDF detection method, this paper introduces N-Gram and Word2vec methods for the first time, a total of three different natural language processing technologies to process and extract URL data. Through a series of experiments, this paper proves that semantic analysis can improve the accuracy of malicious code detection successfully by adjusting parameters of the optimization model. The final experimental results show that the detection rate of malicious URLs by TF-IDF method and N-Gram method combined with various machinelearning models is about 85%, while the detection rate of Word2vec method combined with deep learning model reaches 99%, and the detection accuracy is significantly improved.
In order to carry out the concept of green development and respond to the construction of digital China, it is imperative to transform the energy industry into digital intelligent development. The power grid infrastru...
详细信息
ISBN:
(纸本)9798400707032
In order to carry out the concept of green development and respond to the construction of digital China, it is imperative to transform the energy industry into digital intelligent development. The power grid infrastructure project is regional and complex, and the traditional information architecture is difficult to support its data management and value realization, the application of multi-source and visual data analysis combining with power grid infrastructure engineering data, geological data, meteorological data and so on is developing gradually. The research of power grid infrastructure business management platform based on data layer analysis method, firstly analyzes the power grid infrastructure business demand, then carries out the application design and the construction function, finally carries on the example study. It realizes the unified structured management and visual display of various types of power grid infrastructure resources, breaks the data barriers, makes the heterogeneous data get fusion analysis and application, releases the value of power grid data elements and helps new power systems construct and develop.
暂无评论